让大模型回答前先检查证据是否支持，避免胡说八道。
PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs
- 把检索到的文本拆成小事实，逐个验证答案是否站得住脚。
- 在跨度标注任务上最高提升32.7分准确率，纠错效果显著。
- 适合需要高可信度问答的场景，如医疗、法律领域应用。
检索增强型语言模型虽能获取相关证据，却常在未验证前提的情况下直接给出答案。本文提出PAVE（前提感知的答案验证与修正）机制，作为推理阶段的验证层，用于实现基于证据的问答。PAVE将检索到的上下文分解为与问题相关的原子事实，生成答案草稿，评估该草稿被提取前提支持的程度，并在支持度低时进行修正后再输出。整个过程形成可追溯的决策链条，支持度评分与修改记录均透明可查。在固定检索器和主干模型的前提下，于两个基于证据的问答任务中，PAVE优于简单后处理基线，最大准确率提升达32.7点。结果表明，显式前提提取结合支持度控制的修正机制，可有效增强检索增强型大模型在证据一致性上的表现。
原文摘要 · Abstract (English)
Retrieval-augmented language models can retrieve relevant evidence yet still commit to answers before explicitly checking whether the retrieved context supports the conclusion. We present PAVE (Premise-Grounded Answer Validation and Editing), an inference-time validation layer for evidence-grounded question answering. PAVE decomposes retrieved context into question-conditioned atomic facts, drafts an answer, scores how well that draft is supported by the extracted premises, and revises low-support outputs before finalization. The resulting trace makes answer commitment auditable at the level of explicit premises, support scores, and revision decisions. In controlled ablations with a fixed retriever and backbone, PAVE outperforms simpler post-retrieval baselines in two evidence-grounded QA settings, with the largest gain reaching 32.7 accuracy points on a span-grounded benchmark. We view these findings as proof-of-concept evidence that explicit premise extraction plus support-gated revision can strengthen evidence-grounded consistency in retrieval-augmented LLM systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。